From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
82 lines
2.7 KiB
82 lines
2.7 KiB
WEBVTT |
|
|
|
00:00.830 --> 00:06.770 |
|
The mantra of this course is that the best way to learn is by doing, and we will be doing stuff together |
|
|
|
00:06.770 --> 00:07.340 |
|
throughout. |
|
|
|
00:07.370 --> 00:12.350 |
|
There will be eight commercial projects which will be applying what you're learning to real business |
|
|
|
00:12.350 --> 00:15.380 |
|
problems, and they'll be exercises for you to do the same thing. |
|
|
|
00:15.380 --> 00:21.050 |
|
And I'm hoping that you'll be able to set up GitHub and be able to make your own versions and push them |
|
|
|
00:21.050 --> 00:26.030 |
|
and send me a PR, a pull request, and I'll be able to merge in your code so that other people can |
|
|
|
00:26.030 --> 00:27.320 |
|
see your solutions too. |
|
|
|
00:27.350 --> 00:32.570 |
|
But you'll be able to add this to your GitHub and be able to show yourself that you are building projects |
|
|
|
00:32.570 --> 00:34.790 |
|
to solve real world commercial problems. |
|
|
|
00:34.790 --> 00:38.570 |
|
One of our projects I mentioned is going to be a chatbot assistant. |
|
|
|
00:38.570 --> 00:40.100 |
|
We're going to build one for an airline. |
|
|
|
00:40.100 --> 00:43.400 |
|
It's going to be able to do things like use tools to look up the price of tickets. |
|
|
|
00:43.400 --> 00:48.230 |
|
It's going to make audio and it's going to show pictures like this beautiful pop art version of London |
|
|
|
00:48.230 --> 00:52.490 |
|
showing here on the right as you interact with the chatbot assistant. |
|
|
|
00:52.910 --> 00:58.910 |
|
We're also going to be building rag pipelines, putting vectors of information in a vector data store |
|
|
|
00:58.940 --> 01:03.260 |
|
that you'll have running, and we'll be able to look at things like visualizations of the vectors, |
|
|
|
01:03.260 --> 01:09.920 |
|
mess around with them in 3D space, look into them to understand how different kinds of information |
|
|
|
01:09.920 --> 01:15.980 |
|
get placed in different locations in vector space, and why that is fundamental to Rag retrieval, augmented |
|
|
|
01:15.980 --> 01:16.910 |
|
generation. |
|
|
|
01:16.910 --> 01:21.800 |
|
And then, as I say, the the moment, the big moment in the project will be in week eight, when we |
|
|
|
01:21.800 --> 01:27.620 |
|
will build an Agentic AI solution that will bring together everything that you've learned about through |
|
|
|
01:27.620 --> 01:31.340 |
|
the eight weeks for something which will solve a business problem. |
|
|
|
01:31.640 --> 01:36.260 |
|
And I'll be able to give you some examples of how you can then apply that to solving other business |
|
|
|
01:36.260 --> 01:39.260 |
|
problems that you might face in the future, or that you might have today. |
|
|
|
01:39.320 --> 01:44.660 |
|
And you'll be able to watch as agents collaborate, you'll see the memory of the agents and see what's |
|
|
|
01:44.660 --> 01:47.180 |
|
going on in our agent world. |
|
|
|
01:47.210 --> 01:48.890 |
|
A lot to look forward to.
|
|
|